• Aucun résultat trouvé

Cognitive and Action Sequence Prediction using Deductive Reasoning

N/A
N/A
Protected

Academic year: 2021

Partager "Cognitive and Action Sequence Prediction using Deductive Reasoning"

Copied!
2
0
0

Texte intégral

(1)

ISAE-SUPAERO Conference paper

The 1st International Conference on Cognitive Aircraft

Systems – ICCAS

March 18-19, 2020

https://events.isae-supaero.fr/event/2

Scientific Committee

Mickaël Causse, ISAE-SUPAERO

Caroline Chanel, ISAE-SUPAERO

Jean-Charles Chaudemar, ISAE-SUPAERO

Stéphane Durand, Dassault Aviation

Bruno Patin, Dassault Aviation

Nicolas Devaux, Dassault Aviation

Jean-Louis Gueneau, Dassault Aviation

Claudine Mélan, Université Toulouse Jean-Jaurès

Jean-Paul Imbert, ENAC

Permanent link :

https://doi.org/10.34849/cfsb-t270

Rights / License:

(2)

ICCAS 2020 Cognitive and Action Sequence Pr …

Cognitive and Action Sequence Prediction using

Deductive Reasoning

Content

Early in the process of the development of an aircraft cockpit, although the designers always in-troduce a set of operational procedures with the expectation that all pilots would follow, it is very difficult to guarantee that the flight crew will do exactly they are expected to do. The deviation of the pilots’ operation from the intended procedures may lead to an unsafe situation, and could also be an indication to the inherent reason for the biases in the pilots’ cognitive process. It became very obvious that a tool that could help to predict a comprehensive set of possible operations that the pilots would operate the aircraft will be very useful both in the flight deck design process and pilot training practices.

This paper presents the development of the researches in the “Cognitive and Action Sequence Prediction using Deductive Creation Theory (CASEPREDICT)”. Unlike any human-made system which the response of the system can be predicted to certain degree of accuracy, a human-in-the-loop system is always associated with a great deal of uncertainty issues which comes from the cognitive process of human operators. The researches has been centered around flight crew cog-nitive model and involved the works in the following aspects,

1) The decomposition of the intended tasks into the crew operations in both physical and cognitive activities

2) An analytical process of the dynamic crew situation awareness procedure

3) The biases of decision making process due to the combination and the temporal sequence of the incoming information

4) The temporal and precision uncertainties in operational actions

5) Modeling of the pilot-in-the-loop system and virtual experiments that generate the system be-haviours

6) Experimental methods for obtaining the parameters and characters of the interactions between the pilots and aircraft system

7) The hierarchy pilot response modes

8) The extraction of operational habits and influential factors 9) Training levels and skill transfer

In order to record and analyze the deduced cognitive and action sequence, a set of coding rules was also developed, and further performance and workload analyses can be conducted.

The presented work has been a set of combined research activities since 10 years ago and the re-search results were turned into a software-based development tool. With designated interface to design layout of the flight deck and functional allocation, the program was successfully applied to the development and evaluation of the flight deck, including the investigation of correctness and efficiency of the flight deck function allocation, flight crew workload for given task procedure and the training courses.

Prof. FU, Shan (Department of Automation, SEIEE, Shanghai Jiao Tong University)

;

Dr YIN, Tangwen (Department of Automation, SEIEE, Shanghai Jiao Tong University)

;

Dr HUANG, Dan

;

Dr LU, Yanyu (Department of Automation, SEIEE, Shanghai Jiao Tong University)

;

Dr WANG, Zhen

;

Dr LU, Yi

;

Dr GU, Shimin

;

Mr REN, Bingxuan

;

Mr ZHOU, Yutong

Références

Documents relatifs

The relationship between deductive reasoning and the syntax of language in Broca’s area: A review of the neuroimaging literature.. Annee Psychologique, Centre Henri Pieron/Armand

The original analysis by TIGR provided 625 function predictions (Bult et al., 1996) (37% of the chromosomal genome), with the update increasing them to 809 assignments (Kyrpides et

We find evidence for correspondence with postulate U1, which states that updating with the new fact must ensure that the new fact is a consequence of the update.. We find evidence

Logic Tensor Networks (LTNs) are a deep learning model that comes from the neural-symbolic field: it integrates both logic and data in a neural network to provide support for

Finally, Problems 14 and 15 contain synthetic data generated from two Deterministic Finite State Automata learned using the ALERGIA algorithm [2] on the NLP data sets of Problems 4

Copyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners and it is a condition of

In this paper, we firstly make an Enrichment of dp-idp with Dominance Hierarchy to facilitate the determination of Skyline scores, we propose then the CoSky method (Cosine Skylines)

Proof. We reduce from Positive Exactly 3-Bounded 1-In-3 3-Sat, where each variable appears in exactly three clauses and only positively, each clause contains three positive